Post-Doctoral Research Topic Towards a recommendation system of tourist offers for the Metropole Rouen Normandie

Contexte du poste

The Metropole Rouen Normandie (MRN) is participating in the European Commission's Intelligent Cities Challenge (ICC) ( ICC is an initiative that brings together 136 cities to achieve smart, socially responsible and sustainable growth through advanced technologies. It is a programme that aims to assist participating cities to develop a strategic vision and roadmap for their digital transformation, creating new business opportunities, advancing sustainable developments and improving both digitally and socially.

The MRN fits into the "Green and Digital Transition in Tourism" theme of the challenge, which is geared towards the pursuit of smart and sustainable practices as well as the diversification of the tourism sector. It will provide a local roadmap for green and digital transitions, promote better data sharing and management and encourage investment in new technologies. These actions are motivated by the objective of facilitating new growth opportunities and economic recovery in tourism. 

In addition, the departments of Eure and Seine-Maritime and the Normandy Region are working together to support Rouen's application to become the European Capital of Culture in 2028 (

In this context and in the framework of a current collaboration with the MRN and the Momentech company (, the LITIS of INSA Rouen Normandie is seeking to hire a post-doctoral researcher to propose solutions for

-       enhancing the value of the tourist offer in the MRN, 

-       the development of visitor numbers,  

-       providing a relevant response to visitors to the region

-       maximising the value of tourist destinations in the MRN

-       building visitor and partner loyalty

INSA Rouen Normandie, a public engineering school, actively contributes to the influence of scientific research in Normandy, in France and throughout the world. INSA Rouen Normandie's research laboratories carry out high-level projects in the fields of chemistry, energy, computer science and information systems, applied mathematics, mechanics, materials and process engineering. 

LITIS, the Computer Science, Information Processing and Systems Laboratory, is a research unit in information science and technology attached to the University of Rouen Normandy (URN), the University of Le Havre Normandy (ULHN) and the National Institute of Applied Sciences of Rouen Normandy (INSARN).  Understanding the fundamental nature of information and its representation is at the heart of the LITIS scientific project, which covers a broad spectrum of ICST, from fundamental research to applied fields. The LITIS approach is resolutely multidisciplinary, bringing together practitioners and theoreticians at the junction of computer science, artificial intelligence, signal and image processing and mathematics, with applications in intelligent mobility systems, health information processing and heritage enhancement.

This recruitment is carried out within the framework of the SMARTCAP project, funded by the European Commission through the European Regional Development Fund (ERDF).


The first objective of the project is to bring to light tourist elements that are not well known in the MRN and therefore not well visited. To do this, it is necessary to identify "touristic gems", i.e. places of great interest to visitors. These gems can be cultural or non-cultural sites (hiking, biking, recreation), quality restaurants or lodging, parks, beaches. They may also be unknown, or known by certain types of visitors but not sufficiently highlighted in the itinerary of other visitors likely to appreciate them. 

The second objective of the project is to highlight the offers adapted to the different types of tourists. The idea is to target more precisely the offers proposed to the visitors according to their profile, from the typology of the visitors and the offers and the satisfaction of the different typologies of visitors about these offers. The project will benefit from a massive use of open data, both as an input to the project (use of open data sources on tourism in Normandy and their integration with the MRN's own data to better understand and anticipate future tourist flows in the territory) and as an output (making the results of the project available in "open data").

The development of a system for recommending tourist offers to visitors is the final objective of this project. Different architectures of recommender systems will have to be explored depending on the case study proposed by the MRN. 

Current approaches for the development of recommender systems [1] include different strategies such as collaborative filtering [2], content-based filtering [3] or hybrid approaches, which also integrate knowledge models [4]. In particular, in this last area, we are interested in conversational recommender systems [5] and session-based recommender systems [6], because if, generally, recommendations consider the visitors' profiles, it would also be interesting if the system suggests new places and activities that might suit them but do not exactly match their profile (after all, this is one of the nice aspects of tourism, discovering new places and discovering ourselves :)). To this end, the idea would be that the system could allow visitors to specify certain preferences incrementally based on the recommendations given by the system, i.e. the visitors' needs and preferences would be obtained as part of a feedback loop during a recommendation session, thus improving the next recommendations.



[1] Charu C. Aggarwal. (2016) Recommender Systems: The Textbook (1st. ed.). Springer Publishing Company.

[2] Schafer J.B., Frankowski D., Herlocker J., Sen S. (2007) Collaborative Filtering Recommender Systems. In: Brusilovsky P., Kobsa A., Nejdl W. (eds) The Adaptive Web. Lecture Notes in Computer Science, vol 4321. Springer, Berlin, Heidelberg.

[3] Pazzani M.J., Billsus D. (2007) Content-Based Recommendation Systems. In: Brusilovsky P., Kobsa A., Nejdl W. (eds) The Adaptive Web. Lecture Notes in Computer Science, vol 4321. Springer, Berlin, Heidelberg.

[4]  Negre E. (2015) Systèmes de recommandation – Introduction. ISTE, ISBN : 9781784050863.

[5] Sun, Y., & Zhang, Y. (2018) Conversational Recommender Systems. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval (SIGIR '18). Association for Computing Machinery, New York, NY, USA, 235–244. DOI:

[6]  Wang, S., Cao, L., Wang, Y., Sheng, Q. Z., Orgun, M. A., & Lian, D. (2021). A survey on session-based recommender systems. ACM Computing Surveys (CSUR), 54(7), 1-38.

Comment postuler ?

Duration of the project: 12 months.


Candidate profile:

We are looking for a young doctor of computer science specialised in artificial intelligence with skills in semantic technologies (including the development of ontologies and reasoning models) and recommendation systems. Experience in using and querying open data is a plus.


Prerequisites: Java programming, Python programming


Remuneration: Between 42 and 46 k€ gross salary / year approximately


How to apply

Send CV and cover letter explaining your interest in the post-doc topic to Cecilia Zanni-Merk ( before September 22nd, 2021, for a contract start on November 1st, 2021.